Get the post-compilation status of a project: compile state, diagnostics, pending changes, and module/test summary. Read-only — does not trigger compilation. When wait=true, blocks until compileState is terminal (ok/warnings/errors) and emits MCP progress notifications. Note: compileState reflect...
AI agents call project_status to retrieve information from Openl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves project compilation status without modifying, executing code, deleting data, or affecting finances. The explicit 'read-only' designation and focus on status inspection confirm it is a data retrieval operation with no side effects beyond reading existing state.
From the tool's definition Tool description explicitly states 'Read-only — does not trigger compilation' and describes retrieval of project status information: 'compile state, diagnostics, pending changes, and module/test summary.'
Attacks that exploit this kind of access
Get the post-compilation status of a project: compile state, diagnostics, pending changes, and module/test summary. Read-only — does not trigger compilation. When wait=true, blocks until compileState is terminal (ok/warnings/errors) and emits MCP progress notifications. Note: compileState reflects the last compilation. The studio does not auto-compile on edit (it resets the status), but openl_update_table / openl_append_table / openl_create_project_table all trigger a recompile of the affected table, so this status reflects changes made through those tools. (Edits made by bypassing those tools — e.g. raw REST — won. It is categorised as a Read tool in the Openl MCP Server, which means it retrieves data without modifying state.
Register the Openl MCP server in PolicyLayer and add a rule for project_status: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Openl. Nothing to install.
project_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the project_status rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for project_status. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
project_status is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →